Senior Staff Research Engineer at Google DeepMind focused on Agent Evals and Quality for GenAI model improvement and product development. The role involves developing, evaluating, and optimizing LLM-based agents for complex, multi-step tasks. Responsibilities include constructing quantitative benchmarks and automated evaluation frameworks (e.g., LLM-as-a-judge) to measure agent capabilities in reasoning, planning, and tool use, as well as creating and optimizing data mixes from user feedback for training and fine-tuning agents. The role also requires analyzing agent behavior to identify failure modes and performance bottlenecks.

Senior Quality Engineer for Gemini Enterprise Quality at Google Cloud AI Research. This role involves designing and implementing ML solutions, leveraging ML infrastructure, and focusing on quality assurance for AI products, particularly in specialized ML areas like speech/audio or reinforcement learning. The role requires experience in ML infrastructure, including model deployment and evaluation, and contributes to bringing AI innovations to real-world impact.